MODEL ANALISIS SPEKTRAL CAMPURAN DAN PENDEKATAN CONVOLUTIONAL NEURAL NETWORK OF LONG SHORT-TERM MEMORY UNTUK PEMANTAUAN INDEKS KUALITAS AIR (IKA) SUNGAI

OKTAVIANTI, IKA and Hartono, Yusuf and Sukemi, Sukemi (2024) MODEL ANALISIS SPEKTRAL CAMPURAN DAN PENDEKATAN CONVOLUTIONAL NEURAL NETWORK OF LONG SHORT-TERM MEMORY UNTUK PEMANTAUAN INDEKS KUALITAS AIR (IKA) SUNGAI. Doctoral thesis, Sriwijaya University.

	Image RAMA_21001_03013682025004_COVER.jpg - Cover Image Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (166kB) | Request a copy
	Text RAMA_21001_03013682025004.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
	Text RAMA_21001_03013682025004_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (14MB) | Request a copy
	Text RAMA_21001_03013682025004_0010116401_0003126604_01_front_ref.pdf Download (1MB)
	Text RAMA_21001_03013682025004_0010116401_0003126604_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (788kB) | Request a copy
	Text RAMA_21001_03013682025004_0010116401_0003126604_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (977kB) | Request a copy
	Text RAMA_21001_03013682025004_0010116401_0003126604_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_21001_03013682025004_0010116401_0003126604_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (163kB) | Request a copy
	Text RAMA_21001_03013682025004_0010116401_0003126604_06_REF.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (228kB) | Request a copy
	Text RAMA_21001_03013682025004_0010116401_0003126604_07_LAMP.pdf - Published Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy

Abstract

Water is very important for living creatures and good water quality is one of the pillars of the 17 Pillars of Sustainable Development Goals (SDGs) set by the United Nation. One way to provide an overview of the quality of a water body is to provide an index, which is generally known as the Water Quality Index (WQI). The Water Quality Index has been applied to categorize water quality, namely very good, good, bad, and others. This application is useful for inferring water quality for the community and policy makers in the relevant area. There are 8 (eight) mandatory parameters as components of the WQI calculation, namely Total Suspended Solid (TSS) concentration, degree of acidity (pH), Biological Oxygen Demand (BOD) concentration, Chemical Oxygen Demand (COD) concentration, Dissolved Oxygen (DO), Total concentration Phosphate, Fecal Coliform (E-Coli) concentration and Nitrate concentration (NO3-N). Previously monitoring was still done manually, namely by measuring directly in the field, so it was less effective and efficient. This research aims to explain River WQI Monitoring using the Mixture Spectral Analysis (MSA) Method and ConvLSTM approach and produce a river WQI spectral database through a webgis information system. The research method carried out was in-situ measurement of 8 mandatory water quality measurement parameters which were tested in the laboratory in the 2021 - 2023 period. Then spectral standardization was carried out on the data results in the field and analyzed using mixed spectra. The data is then processed using the ConvLSTM technique to produce a River IKA monitoring model. This research produces a river IKA monitoring model using the ASC method, namely a band-345 model with a visible color spectrum which represents the Met (M) and Light (R) Pollution Index which is Blue and wavelengths (spectrum) ranging from 0.53 µm to with 0.88 µm. The results of testing the application of the hybrid ConvLSTM model with data on 8 mandatory parameters for River IKA measurements at 30 watershed monitoring points in Muratara Regency from 2021 to 2023, produced the best modeling seen in taking DO concentration, followed by pH, TSS, BOD, COD, E-Coli, TP, and NO3-N. The modeling technique with ConvLSTM proved to be quite accurate, producing an R2 value of 0.9603; 0.9582; 0.9657 for all parameters with training dataset and testing dataset. The model produces average MSE and RMSE test values of 0.00080 and 0.00085 respectively for all water parameters. The performance of this model is acceptable and can be used as a baseline for monitoring rivers not only in South Sumatra Province, but also throughout Indonesia.

Item Type:	Thesis (Doctoral)
Uncontrolled Keywords:	Water Quality Index, Mixture Spectral Analysis, Remote Sensing, Deep Learning, Convolutional of Long Short-Term Memory
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General) T Technology > T Technology (General) > T58.5-58.64 Information technology > T58.5 General works Management information systems Cf. HD30.213 Industrial management Cf. HF5549.5.C6+ Communication in personnel management Cf. TS158.6 Automatic data collection systems (Production control)
Divisions:	03-Faculty of Engineering > 21001-Engineering Science (S3)
Depositing User:	Ika Oktavianti
Date Deposited:	19 Jul 2024 04:13
Last Modified:	19 Jul 2024 04:13
URI:	http://repository.unsri.ac.id/id/eprint/151676

Actions (login required)

View Item